Benchmark

ARC-AGI-2

Measures: Novel grid-transformation puzzles: from a few input/output examples a system must produce the exact output grid for a test input; scored as % of tasks solved on the semi-private set, with cost per task.

Maintainer
ARC Prize Foundation
Introduced
2025
Status
Active
Saturation
Saturated
Typical provenance
Independent
In scoring set
No

PaperOfficial leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.